Hugging Face's logo

jxm
/
t5_base__llama-7b__one-million-instructions__suffix__2__50epoch

Transformers
PyTorch
Model card Files Community
jxm commited on
Commit
322394c
·
1 Parent(s): 2ae77d7

Upload model

Browse files
Files changed (5) hide show
  1. config.json +159 -0
  2. generation_config.json +4 -0
  3. pytorch_model-00001-of-00002.bin +3 -0
  4. pytorch_model-00002-of-00002.bin +3 -0
  5. pytorch_model.bin.index.json +567 -0
config.json ADDED
@@ -0,0 +1,159 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_frozen": true,
3
+ "_n_gpu": 1,
4
+ "adafactor": false,
5
+ "adam_beta1": 0.9,
6
+ "adam_beta2": 0.999,
7
+ "adam_epsilon": 1e-06,
8
+ "architectures": [
9
+ "InversionFromLogitsModel"
10
+ ],
11
+ "auto_find_batch_size": false,
12
+ "bf16": true,
13
+ "bf16_full_eval": false,
14
+ "cache_dir": null,
15
+ "cheat_on_train_hypotheses": false,
16
+ "config_name": null,
17
+ "config_overrides": null,
18
+ "corrector_ignore_hypothesis_embedding": false,
19
+ "corrector_model_alias": "dpr_nq__msl32_beta",
20
+ "data_seed": null,
21
+ "dataloader_drop_last": false,
22
+ "dataloader_num_workers": 0,
23
+ "dataloader_pin_memory": true,
24
+ "dataset_name": "one_million_instructions",
25
+ "ddp_backend": null,
26
+ "ddp_broadcast_buffers": null,
27
+ "ddp_bucket_cap_mb": null,
28
+ "ddp_find_unused_parameters": false,
29
+ "ddp_timeout": 1800,
30
+ "debug": [],
31
+ "decoder_dropout_disabled": false,
32
+ "deepspeed": null,
33
+ "deepspeed_plugin": null,
34
+ "disable_tqdm": true,
35
+ "dispatch_batches": null,
36
+ "do_eval": false,
37
+ "do_predict": false,
38
+ "do_train": false,
39
+ "embedder_fake_with_zeros": false,
40
+ "embedder_model_api": null,
41
+ "embedder_model_name": "meta-llama/Llama-2-7b-hf",
42
+ "embedder_no_grad": true,
43
+ "embedder_torch_dtype": "bfloat16",
44
+ "embedding_transform_strategy": "repeat",
45
+ "embedding_zero_except_topk": null,
46
+ "embeddings_from_layer_n": null,
47
+ "encoder_dropout_disabled": false,
48
+ "eval_accumulation_steps": null,
49
+ "eval_delay": 0,
50
+ "eval_steps": 3125,
51
+ "evaluation_strategy": "steps",
52
+ "exp_group_name": "",
53
+ "exp_name": "",
54
+ "experiment": "inversion_from_logits",
55
+ "fp16": false,
56
+ "fp16_backend": "auto",
57
+ "fp16_full_eval": false,
58
+ "fp16_opt_level": "O1",
59
+ "freeze_strategy": "none",
60
+ "fsdp": [],
61
+ "fsdp_config": {
62
+ "min_num_params": 0,
63
+ "xla": false,
64
+ "xla_fsdp_grad_ckpt": false
65
+ },
66
+ "fsdp_min_num_params": 0,
67
+ "fsdp_transformer_layer_cls_to_wrap": null,
68
+ "full_determinism": false,
69
+ "gradient_accumulation_steps": 1,
70
+ "gradient_checkpointing": false,
71
+ "greater_is_better": false,
72
+ "group_by_length": true,
73
+ "half_precision_backend": "auto",
74
+ "hub_always_push": false,
75
+ "hub_model_id": null,
76
+ "hub_private_repo": false,
77
+ "hub_strategy": "every_save",
78
+ "hub_token": null,
79
+ "ignore_data_skip": false,
80
+ "include_inputs_for_metrics": true,
81
+ "jit_mode_eval": false,
82
+ "label_names": null,
83
+ "label_smoothing_factor": 0.0,
84
+ "learning_rate": 0.0002,
85
+ "length_column_name": "length",
86
+ "load_best_model_at_end": true,
87
+ "local_rank": 0,
88
+ "log_level": "passive",
89
+ "log_level_replica": "warning",
90
+ "log_on_each_node": true,
91
+ "logging_dir": "saves/runs/Sep27_21-35-28_Jack2",
92
+ "logging_first_step": false,
93
+ "logging_nan_inf_filter": true,
94
+ "logging_steps": 50,
95
+ "logging_strategy": "steps",
96
+ "lr_scheduler_type": "constant_with_warmup",
97
+ "max_eval_samples": 500,
98
+ "max_grad_norm": 1.0,
99
+ "max_seq_length": 64,
100
+ "max_steps": -1,
101
+ "metric_for_best_model": "one_million_instructions_loss",
102
+ "mock_embedder": false,
103
+ "model_name_or_path": "t5-base",
104
+ "model_revision": "main",
105
+ "mp_parameters": "",
106
+ "no_cuda": false,
107
+ "num_repeat_tokens": 16,
108
+ "num_train_epochs": 100.0,
109
+ "optim": "adamw_torch",
110
+ "optim_args": null,
111
+ "output_dir": "saves/4985d3f58e9afefa4d8a8066cd1a348b/c27736d27b2a079364f53134f8bb39d9",
112
+ "overwrite_output_dir": false,
113
+ "past_index": -1,
114
+ "per_device_eval_batch_size": 64,
115
+ "per_device_train_batch_size": 256,
116
+ "per_gpu_eval_batch_size": null,
117
+ "per_gpu_train_batch_size": null,
118
+ "prediction_loss_only": false,
119
+ "push_to_hub": false,
120
+ "push_to_hub_model_id": null,
121
+ "push_to_hub_organization": null,
122
+ "push_to_hub_token": null,
123
+ "ray_scope": "last",
124
+ "remove_unused_columns": false,
125
+ "report_to": [],
126
+ "resume_from_checkpoint": null,
127
+ "run_name": "saves",
128
+ "save_on_each_node": false,
129
+ "save_safetensors": false,
130
+ "save_steps": 1000,
131
+ "save_strategy": "steps",
132
+ "save_total_limit": 1,
133
+ "seed": 42,
134
+ "sharded_ddp": [],
135
+ "skip_memory_metrics": true,
136
+ "steps_per_epoch": 500000,
137
+ "suffix_conditioning": true,
138
+ "tf32": null,
139
+ "tokenizer_name": null,
140
+ "torch_compile": false,
141
+ "torch_compile_backend": null,
142
+ "torch_compile_mode": null,
143
+ "torch_dtype": "float32",
144
+ "torchdynamo": null,
145
+ "tpu_metrics_debug": false,
146
+ "tpu_num_cores": null,
147
+ "transformers_version": "4.33.2",
148
+ "use_cpu": false,
149
+ "use_frozen_embeddings_as_input": true,
150
+ "use_ipex": false,
151
+ "use_legacy_prediction_loop": false,
152
+ "use_less_data": -1,
153
+ "use_lora": false,
154
+ "use_mps_device": false,
155
+ "use_wandb": false,
156
+ "warmup_ratio": 0.0,
157
+ "warmup_steps": 12500,
158
+ "weight_decay": 0.0
159
+ }
generation_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "transformers_version": "4.33.2"
4
+ }
pytorch_model-00001-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23329d95c52742ceb59d37cd9b20856764accbf622c2afc493a341da9412e73b
3
+ size 10000055235
pytorch_model-00002-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30c8628db732df316d38d384979dbd7df044b2437f596fcbeeb0a895772946d7
3
+ size 5010358968
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,567 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 15010212864
4
+ },
5
+ "weight_map": {
6
+ "embedder.lm_head.weight": "pytorch_model-00002-of-00002.bin",
7
+ "embedder.model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
8
+ "embedder.model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
9
+ "embedder.model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
10
+ "embedder.model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
11
+ "embedder.model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
12
+ "embedder.model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
13
+ "embedder.model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
14
+ "embedder.model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
15
+ "embedder.model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
16
+ "embedder.model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
17
+ "embedder.model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
18
+ "embedder.model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
19
+ "embedder.model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
20
+ "embedder.model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
21
+ "embedder.model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
22
+ "embedder.model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
23
+ "embedder.model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
24
+ "embedder.model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
25
+ "embedder.model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
26
+ "embedder.model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
27
+ "embedder.model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
28
+ "embedder.model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
29
+ "embedder.model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
30
+ "embedder.model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
31
+ "embedder.model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
32
+ "embedder.model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
33
+ "embedder.model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
34
+ "embedder.model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
35
+ "embedder.model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
36
+ "embedder.model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
37
+ "embedder.model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
38
+ "embedder.model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
39
+ "embedder.model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
40
+ "embedder.model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
41
+ "embedder.model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
42
+ "embedder.model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
43
+ "embedder.model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
44
+ "embedder.model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
45
+ "embedder.model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
46
+ "embedder.model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
47
+ "embedder.model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
48
+ "embedder.model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
49
+ "embedder.model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
50
+ "embedder.model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
51
+ "embedder.model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
52
+ "embedder.model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
53
+ "embedder.model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
54
+ "embedder.model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
55
+ "embedder.model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
56
+ "embedder.model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
57
+ "embedder.model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
58
+ "embedder.model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
59
+ "embedder.model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
60
+ "embedder.model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
61
+ "embedder.model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
62
+ "embedder.model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
63
+ "embedder.model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
64
+ "embedder.model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
65
+ "embedder.model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
66
+ "embedder.model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
67
+ "embedder.model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
68
+ "embedder.model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
69
+ "embedder.model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
70
+ "embedder.model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
71
+ "embedder.model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
72
+ "embedder.model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
73
+ "embedder.model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
74
+ "embedder.model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
75
+ "embedder.model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
76
+ "embedder.model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
77
+ "embedder.model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
78
+ "embedder.model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
79
+ "embedder.model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
80
+ "embedder.model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
81
+ "embedder.model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
82
+ "embedder.model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
83
+ "embedder.model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
84
+ "embedder.model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
85
+ "embedder.model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
86
+ "embedder.model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
87
+ "embedder.model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
88
+ "embedder.model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
89
+ "embedder.model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
90
+ "embedder.model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
91
+ "embedder.model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
92
+ "embedder.model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
93
+ "embedder.model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
94
+ "embedder.model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
95
+ "embedder.model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
96
+ "embedder.model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
97
+ "embedder.model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
98
+ "embedder.model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
99
+ "embedder.model.layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
100
+ "embedder.model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
101
+ "embedder.model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
102
+ "embedder.model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
103
+ "embedder.model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
104
+ "embedder.model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
105
+ "embedder.model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
106
+ "embedder.model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
107
+ "embedder.model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
108
+ "embedder.model.layers.19.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
109
+ "embedder.model.layers.19.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
110
+ "embedder.model.layers.19.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
111
+ "embedder.model.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
112
+ "embedder.model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
113
+ "embedder.model.layers.19.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
114
+ "embedder.model.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
115
+ "embedder.model.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
116
+ "embedder.model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
117
+ "embedder.model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
118
+ "embedder.model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
119
+ "embedder.model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
120
+ "embedder.model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
121
+ "embedder.model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
122
+ "embedder.model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
123
+ "embedder.model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
124
+ "embedder.model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
125
+ "embedder.model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
126
+ "embedder.model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
127
+ "embedder.model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
128
+ "embedder.model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
129
+ "embedder.model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
130
+ "embedder.model.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
131
+ "embedder.model.layers.20.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
132
+ "embedder.model.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
133
+ "embedder.model.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
134
+ "embedder.model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
135
+ "embedder.model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
136
+ "embedder.model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
137
+ "embedder.model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
138
+ "embedder.model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
139
+ "embedder.model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
140
+ "embedder.model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
141
+ "embedder.model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
142
+ "embedder.model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
143
+ "embedder.model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
144
+ "embedder.model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
145
+ "embedder.model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
146
+ "embedder.model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
147
+ "embedder.model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
148
+ "embedder.model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
149
+ "embedder.model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
150
+ "embedder.model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
151
+ "embedder.model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
152
+ "embedder.model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
153
+ "embedder.model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
154
+ "embedder.model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
155
+ "embedder.model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
156
+ "embedder.model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
157
+ "embedder.model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
158
+ "embedder.model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
159
+ "embedder.model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
160
+ "embedder.model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
161
+ "embedder.model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
162
+ "embedder.model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
163
+ "embedder.model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
164
+ "embedder.model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
165
+ "embedder.model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
166
+ "embedder.model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
167
+ "embedder.model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
168
+ "embedder.model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
169
+ "embedder.model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
170
+ "embedder.model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
171
+ "embedder.model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
172
+ "embedder.model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
173
+ "embedder.model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
174
+ "embedder.model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
175
+ "embedder.model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
176
+ "embedder.model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
177
+ "embedder.model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
178
+ "embedder.model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
179
+ "embedder.model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
180
+ "embedder.model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
181
+ "embedder.model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
182
+ "embedder.model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
183
+ "embedder.model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
184
+ "embedder.model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
185
+ "embedder.model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
186
+ "embedder.model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
187
+ "embedder.model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
188
+ "embedder.model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
189
+ "embedder.model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
190
+ "embedder.model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
191
+ "embedder.model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
192
+ "embedder.model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
193
+ "embedder.model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
194
+ "embedder.model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
195
+ "embedder.model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
196
+ "embedder.model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
197
+ "embedder.model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
198
+ "embedder.model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
199
+ "embedder.model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
200
+ "embedder.model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
201
+ "embedder.model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
202
+ "embedder.model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
203
+ "embedder.model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
204
+ "embedder.model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
205
+ "embedder.model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
206
+ "embedder.model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
207
+ "embedder.model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
208
+ "embedder.model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
209
+ "embedder.model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
210
+ "embedder.model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
211
+ "embedder.model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
212
+ "embedder.model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
213
+ "embedder.model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
214
+ "embedder.model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
215
+ "embedder.model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
216
+ "embedder.model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
217
+ "embedder.model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
218
+ "embedder.model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
219
+ "embedder.model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
220
+ "embedder.model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
221
+ "embedder.model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
222
+ "embedder.model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
223
+ "embedder.model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
224
+ "embedder.model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
225
+ "embedder.model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
226
+ "embedder.model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
227
+ "embedder.model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
228
+ "embedder.model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
229
+ "embedder.model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
230
+ "embedder.model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
231
+ "embedder.model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
232
+ "embedder.model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
233
+ "embedder.model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
234
+ "embedder.model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
235
+ "embedder.model.layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
236
+ "embedder.model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
237
+ "embedder.model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
238
+ "embedder.model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
239
+ "embedder.model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
240
+ "embedder.model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
241
+ "embedder.model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
242
+ "embedder.model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
243
+ "embedder.model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
244
+ "embedder.model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
245
+ "embedder.model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
246
+ "embedder.model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
247
+ "embedder.model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
248
+ "embedder.model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
249
+ "embedder.model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
250
+ "embedder.model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
251
+ "embedder.model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
252
+ "embedder.model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
253
+ "embedder.model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
254
+ "embedder.model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
255
+ "embedder.model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
256
+ "embedder.model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
257
+ "embedder.model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
258
+ "embedder.model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
259
+ "embedder.model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
260
+ "embedder.model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
261
+ "embedder.model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
262
+ "embedder.model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
263
+ "embedder.model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
264
+ "embedder.model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
265
+ "embedder.model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
266
+ "embedder.model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
267
+ "embedder.model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
268
+ "embedder.model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
269
+ "embedder.model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
270
+ "embedder.model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
271
+ "embedder.model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
272
+ "embedder.model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
273
+ "embedder.model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
274
+ "embedder.model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
275
+ "embedder.model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
276
+ "embedder.model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
277
+ "embedder.model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
278
+ "embedder.model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
279
+ "embedder.model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
280
+ "embedder.model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
281
+ "embedder.model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
282
+ "embedder.model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
283
+ "embedder.model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
284
+ "embedder.model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
285
+ "embedder.model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
286
+ "embedder.model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
287
+ "embedder.model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
288
+ "embedder.model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
289
+ "embedder.model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
290
+ "embedder.model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
291
+ "embedder.model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
292
+ "embedder.model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
293
+ "embedder.model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
294
+ "embedder.model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
295
+ "embedder.model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
296
+ "embedder.model.norm.weight": "pytorch_model-00002-of-00002.bin",
297
+ "embedding_transform.0.bias": "pytorch_model-00001-of-00002.bin",
298
+ "embedding_transform.0.weight": "pytorch_model-00001-of-00002.bin",
299
+ "embedding_transform.3.bias": "pytorch_model-00001-of-00002.bin",
300
+ "embedding_transform.3.weight": "pytorch_model-00001-of-00002.bin",
301
+ "encoder_decoder.decoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
302
+ "encoder_decoder.decoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
303
+ "encoder_decoder.decoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
304
+ "encoder_decoder.decoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00001-of-00002.bin",
305
+ "encoder_decoder.decoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
306
+ "encoder_decoder.decoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
307
+ "encoder_decoder.decoder.block.0.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
308
+ "encoder_decoder.decoder.block.0.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
309
+ "encoder_decoder.decoder.block.0.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
310
+ "encoder_decoder.decoder.block.0.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
311
+ "encoder_decoder.decoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
312
+ "encoder_decoder.decoder.block.0.layer.2.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
313
+ "encoder_decoder.decoder.block.0.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
314
+ "encoder_decoder.decoder.block.0.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
315
+ "encoder_decoder.decoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
316
+ "encoder_decoder.decoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
317
+ "encoder_decoder.decoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
318
+ "encoder_decoder.decoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
319
+ "encoder_decoder.decoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
320
+ "encoder_decoder.decoder.block.1.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
321
+ "encoder_decoder.decoder.block.1.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
322
+ "encoder_decoder.decoder.block.1.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
323
+ "encoder_decoder.decoder.block.1.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
324
+ "encoder_decoder.decoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
325
+ "encoder_decoder.decoder.block.1.layer.2.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
326
+ "encoder_decoder.decoder.block.1.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
327
+ "encoder_decoder.decoder.block.1.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
328
+ "encoder_decoder.decoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
329
+ "encoder_decoder.decoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
330
+ "encoder_decoder.decoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
331
+ "encoder_decoder.decoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
332
+ "encoder_decoder.decoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
333
+ "encoder_decoder.decoder.block.10.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
334
+ "encoder_decoder.decoder.block.10.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
335
+ "encoder_decoder.decoder.block.10.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
336
+ "encoder_decoder.decoder.block.10.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
337
+ "encoder_decoder.decoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
338
+ "encoder_decoder.decoder.block.10.layer.2.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
339
+ "encoder_decoder.decoder.block.10.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
340
+ "encoder_decoder.decoder.block.10.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
341
+ "encoder_decoder.decoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
342
+ "encoder_decoder.decoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
343
+ "encoder_decoder.decoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
344
+ "encoder_decoder.decoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
345
+ "encoder_decoder.decoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
346
+ "encoder_decoder.decoder.block.11.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
347
+ "encoder_decoder.decoder.block.11.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
348
+ "encoder_decoder.decoder.block.11.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
349
+ "encoder_decoder.decoder.block.11.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
350
+ "encoder_decoder.decoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
351
+ "encoder_decoder.decoder.block.11.layer.2.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
352
+ "encoder_decoder.decoder.block.11.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
353
+ "encoder_decoder.decoder.block.11.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
354
+ "encoder_decoder.decoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
355
+ "encoder_decoder.decoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
356
+ "encoder_decoder.decoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
357
+ "encoder_decoder.decoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
358
+ "encoder_decoder.decoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
359
+ "encoder_decoder.decoder.block.2.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
360
+ "encoder_decoder.decoder.block.2.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
361
+ "encoder_decoder.decoder.block.2.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
362
+ "encoder_decoder.decoder.block.2.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
363
+ "encoder_decoder.decoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
364
+ "encoder_decoder.decoder.block.2.layer.2.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
365
+ "encoder_decoder.decoder.block.2.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
366
+ "encoder_decoder.decoder.block.2.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
367
+ "encoder_decoder.decoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
368
+ "encoder_decoder.decoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
369
+ "encoder_decoder.decoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
370
+ "encoder_decoder.decoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
371
+ "encoder_decoder.decoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
372
+ "encoder_decoder.decoder.block.3.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
373
+ "encoder_decoder.decoder.block.3.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
374
+ "encoder_decoder.decoder.block.3.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
375
+ "encoder_decoder.decoder.block.3.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
376
+ "encoder_decoder.decoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
377
+ "encoder_decoder.decoder.block.3.layer.2.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
378
+ "encoder_decoder.decoder.block.3.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
379
+ "encoder_decoder.decoder.block.3.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
380
+ "encoder_decoder.decoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
381
+ "encoder_decoder.decoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
382
+ "encoder_decoder.decoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
383
+ "encoder_decoder.decoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
384
+ "encoder_decoder.decoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
385
+ "encoder_decoder.decoder.block.4.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
386
+ "encoder_decoder.decoder.block.4.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
387
+ "encoder_decoder.decoder.block.4.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
388
+ "encoder_decoder.decoder.block.4.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
389
+ "encoder_decoder.decoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
390
+ "encoder_decoder.decoder.block.4.layer.2.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
391
+ "encoder_decoder.decoder.block.4.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
392
+ "encoder_decoder.decoder.block.4.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
393
+ "encoder_decoder.decoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
394
+ "encoder_decoder.decoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
395
+ "encoder_decoder.decoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
396
+ "encoder_decoder.decoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
397
+ "encoder_decoder.decoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
398
+ "encoder_decoder.decoder.block.5.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
399
+ "encoder_decoder.decoder.block.5.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
400
+ "encoder_decoder.decoder.block.5.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
401
+ "encoder_decoder.decoder.block.5.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
402
+ "encoder_decoder.decoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
403
+ "encoder_decoder.decoder.block.5.layer.2.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
404
+ "encoder_decoder.decoder.block.5.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
405
+ "encoder_decoder.decoder.block.5.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
406
+ "encoder_decoder.decoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
407
+ "encoder_decoder.decoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
408
+ "encoder_decoder.decoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
409
+ "encoder_decoder.decoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
410
+ "encoder_decoder.decoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
411
+ "encoder_decoder.decoder.block.6.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
412
+ "encoder_decoder.decoder.block.6.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
413
+ "encoder_decoder.decoder.block.6.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
414
+ "encoder_decoder.decoder.block.6.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
415
+ "encoder_decoder.decoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
416
+ "encoder_decoder.decoder.block.6.layer.2.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
417
+ "encoder_decoder.decoder.block.6.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
418
+ "encoder_decoder.decoder.block.6.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
419
+ "encoder_decoder.decoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
420
+ "encoder_decoder.decoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
421
+ "encoder_decoder.decoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
422
+ "encoder_decoder.decoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
423
+ "encoder_decoder.decoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
424
+ "encoder_decoder.decoder.block.7.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
425
+ "encoder_decoder.decoder.block.7.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
426
+ "encoder_decoder.decoder.block.7.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
427
+ "encoder_decoder.decoder.block.7.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
428
+ "encoder_decoder.decoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
429
+ "encoder_decoder.decoder.block.7.layer.2.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
430
+ "encoder_decoder.decoder.block.7.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
431
+ "encoder_decoder.decoder.block.7.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
432
+ "encoder_decoder.decoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
433
+ "encoder_decoder.decoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
434
+ "encoder_decoder.decoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
435
+ "encoder_decoder.decoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
436
+ "encoder_decoder.decoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
437
+ "encoder_decoder.decoder.block.8.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
438
+ "encoder_decoder.decoder.block.8.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
439
+ "encoder_decoder.decoder.block.8.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
440
+ "encoder_decoder.decoder.block.8.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
441
+ "encoder_decoder.decoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
442
+ "encoder_decoder.decoder.block.8.layer.2.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
443
+ "encoder_decoder.decoder.block.8.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
444
+ "encoder_decoder.decoder.block.8.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
445
+ "encoder_decoder.decoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
446
+ "encoder_decoder.decoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
447
+ "encoder_decoder.decoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
448
+ "encoder_decoder.decoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
449
+ "encoder_decoder.decoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
450
+ "encoder_decoder.decoder.block.9.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
451
+ "encoder_decoder.decoder.block.9.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
452
+ "encoder_decoder.decoder.block.9.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
453
+ "encoder_decoder.decoder.block.9.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
454
+ "encoder_decoder.decoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
455
+ "encoder_decoder.decoder.block.9.layer.2.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
456
+ "encoder_decoder.decoder.block.9.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
457
+ "encoder_decoder.decoder.block.9.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
458
+ "encoder_decoder.decoder.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
459
+ "encoder_decoder.decoder.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
460
+ "encoder_decoder.encoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
461
+ "encoder_decoder.encoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
462
+ "encoder_decoder.encoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
463
+ "encoder_decoder.encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00001-of-00002.bin",
464
+ "encoder_decoder.encoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
465
+ "encoder_decoder.encoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
466
+ "encoder_decoder.encoder.block.0.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
467
+ "encoder_decoder.encoder.block.0.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
468
+ "encoder_decoder.encoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
469
+ "encoder_decoder.encoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
470
+ "encoder_decoder.encoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
471
+ "encoder_decoder.encoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
472
+ "encoder_decoder.encoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
473
+ "encoder_decoder.encoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
474
+ "encoder_decoder.encoder.block.1.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
475
+ "encoder_decoder.encoder.block.1.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
476
+ "encoder_decoder.encoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
477
+ "encoder_decoder.encoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
478
+ "encoder_decoder.encoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
479
+ "encoder_decoder.encoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
480
+ "encoder_decoder.encoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
481
+ "encoder_decoder.encoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
482
+ "encoder_decoder.encoder.block.10.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
483
+ "encoder_decoder.encoder.block.10.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
484
+ "encoder_decoder.encoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
485
+ "encoder_decoder.encoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
486
+ "encoder_decoder.encoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
487
+ "encoder_decoder.encoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
488
+ "encoder_decoder.encoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
489
+ "encoder_decoder.encoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
490
+ "encoder_decoder.encoder.block.11.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
491
+ "encoder_decoder.encoder.block.11.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
492
+ "encoder_decoder.encoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
493
+ "encoder_decoder.encoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
494
+ "encoder_decoder.encoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
495
+ "encoder_decoder.encoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
496
+ "encoder_decoder.encoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
497
+ "encoder_decoder.encoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
498
+ "encoder_decoder.encoder.block.2.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
499
+ "encoder_decoder.encoder.block.2.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
500
+ "encoder_decoder.encoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
501
+ "encoder_decoder.encoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
502
+ "encoder_decoder.encoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
503
+ "encoder_decoder.encoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
504
+ "encoder_decoder.encoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
505
+ "encoder_decoder.encoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
506
+ "encoder_decoder.encoder.block.3.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
507
+ "encoder_decoder.encoder.block.3.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
508
+ "encoder_decoder.encoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
509
+ "encoder_decoder.encoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
510
+ "encoder_decoder.encoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
511
+ "encoder_decoder.encoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
512
+ "encoder_decoder.encoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
513
+ "encoder_decoder.encoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
514
+ "encoder_decoder.encoder.block.4.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
515
+ "encoder_decoder.encoder.block.4.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
516
+ "encoder_decoder.encoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
517
+ "encoder_decoder.encoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
518
+ "encoder_decoder.encoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
519
+ "encoder_decoder.encoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
520
+ "encoder_decoder.encoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
521
+ "encoder_decoder.encoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
522
+ "encoder_decoder.encoder.block.5.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
523
+ "encoder_decoder.encoder.block.5.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
524
+ "encoder_decoder.encoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
525
+ "encoder_decoder.encoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
526
+ "encoder_decoder.encoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
527
+ "encoder_decoder.encoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
528
+ "encoder_decoder.encoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
529
+ "encoder_decoder.encoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
530
+ "encoder_decoder.encoder.block.6.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
531
+ "encoder_decoder.encoder.block.6.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
532
+ "encoder_decoder.encoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
533
+ "encoder_decoder.encoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
534
+ "encoder_decoder.encoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
535
+ "encoder_decoder.encoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
536
+ "encoder_decoder.encoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
537
+ "encoder_decoder.encoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
538
+ "encoder_decoder.encoder.block.7.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
539
+ "encoder_decoder.encoder.block.7.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
540
+ "encoder_decoder.encoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
541
+ "encoder_decoder.encoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
542
+ "encoder_decoder.encoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
543
+ "encoder_decoder.encoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
544
+ "encoder_decoder.encoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
545
+ "encoder_decoder.encoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
546
+ "encoder_decoder.encoder.block.8.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
547
+ "encoder_decoder.encoder.block.8.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
548
+ "encoder_decoder.encoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
549
+ "encoder_decoder.encoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
550
+ "encoder_decoder.encoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
551
+ "encoder_decoder.encoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
552
+ "encoder_decoder.encoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
553
+ "encoder_decoder.encoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
554
+ "encoder_decoder.encoder.block.9.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
555
+ "encoder_decoder.encoder.block.9.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
556
+ "encoder_decoder.encoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
557
+ "encoder_decoder.encoder.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
558
+ "encoder_decoder.encoder.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
559
+ "encoder_decoder.lm_head.weight": "pytorch_model-00001-of-00002.bin",
560
+ "encoder_decoder.shared.weight": "pytorch_model-00001-of-00002.bin",
561
+ "sequence_weights": "pytorch_model-00001-of-00002.bin",
562
+ "suffix_transform.0.bias": "pytorch_model-00002-of-00002.bin",
563
+ "suffix_transform.0.weight": "pytorch_model-00002-of-00002.bin",
564
+ "suffix_transform.2.bias": "pytorch_model-00002-of-00002.bin",
565
+ "suffix_transform.2.weight": "pytorch_model-00002-of-00002.bin"
566
+ }
567
+ }